TY - GEN
T1 - The Data Behind the Model
T2 - 3rd International Workshop on Foundation Models for Medical Artificial General Intelligence, MedAGI 2025, Held in Conjunction with the 28th International conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
AU - Ghamizi, Salah
AU - Kanli, Georgia
AU - Perquin, Magali
AU - Keunen, Olivier
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2025/10/12
Y1 - 2025/10/12
N2 - Foundation Models (FMs) have revolutionized machine learning in medical imaging, yet their application to brain imaging remains limited and fragmented. Despite the availability of diverse and extensive neuroimaging datasets, most FM research has focused narrowly on a handful of tasks, mainly tumor classification and segmentation, while neglecting prevalent neurological disorders such as ADHD and early-stage Parkinson’s disease. In this work, we present the largest and most comprehensive atlas of brain imaging datasets to date, comprising 151 datasets and over 541k volumetric imaging studies across a wide range of modalities and pathologies. Our meta-analysis of 86 brain imaging FMs reveals a disproportionate reliance on structural MRI and a small set of popular datasets, along with critical blind spots in both disease coverage and imaging modalities. We identify systemic challenges, including inconsistent model evaluation protocols, heterogeneous data formats, and limited availability. All of which hinder reproducibility, scalability, and clinical translation. Our publicly available atlases pave the way for more robust, scalable, and clinically meaningful FMs in brain imaging.
AB - Foundation Models (FMs) have revolutionized machine learning in medical imaging, yet their application to brain imaging remains limited and fragmented. Despite the availability of diverse and extensive neuroimaging datasets, most FM research has focused narrowly on a handful of tasks, mainly tumor classification and segmentation, while neglecting prevalent neurological disorders such as ADHD and early-stage Parkinson’s disease. In this work, we present the largest and most comprehensive atlas of brain imaging datasets to date, comprising 151 datasets and over 541k volumetric imaging studies across a wide range of modalities and pathologies. Our meta-analysis of 86 brain imaging FMs reveals a disproportionate reliance on structural MRI and a small set of popular datasets, along with critical blind spots in both disease coverage and imaging modalities. We identify systemic challenges, including inconsistent model evaluation protocols, heterogeneous data formats, and limited availability. All of which hinder reproducibility, scalability, and clinical translation. Our publicly available atlases pave the way for more robust, scalable, and clinically meaningful FMs in brain imaging.
KW - Brain diseases
KW - Foundation Models
KW - Medical Imaging
UR - https://www.scopus.com/pages/publications/105020012178
U2 - 10.1007/978-3-032-07845-2_11
DO - 10.1007/978-3-032-07845-2_11
M3 - Conference contribution
AN - SCOPUS:105020012178
SN - 9783032078445
T3 - Lecture Notes in Computer Science
SP - 109
EP - 119
BT - Foundation Models for General Medical AI - 3rd International Workshop, MedAGI 2025, Held in Conjunction with MICCAI 2025, Proceedings
A2 - Jeong, Won-Ki
A2 - Kim, Hyunwoo J.
A2 - Deng, Zhongying
A2 - Shen, Yiqing
A2 - Aviles-Rivero, Angelica I
A2 - Zhang, Shaoting
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 27 September 2025 through 27 September 2025
ER -